Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Mathematical conditions/reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assets
    -0.07
     BL
    -0.07
    <B
    -0.07
     textures
    -0.07
    !!.
    -0.07
     energia
    -0.07
    Combo
    -0.07
    .roll
    -0.07
     prefer
    -0.07
     rival
    -0.07
    POSITIVE LOGITS
     stereotype
    0.09
     Handlung
    0.08
     conjunct
    0.08
    elernt
    0.08
    ，对
    0.08
    _context
    0.08
    contexts
    0.08
    CAUSE
    0.08
    。因此
    0.08
     genie
    0.08
    Act Density 0.053%

    No Known Activations